apiVersion: apps/v1 kind: Deployment metadata: name: '{{ .Release.Name }}' labels: app: '{{ .Release.Name }}' spec: replicas: 1 selector: matchLabels: app: '{{ .Release.Name }}' template: metadata: labels: app: '{{ .Release.Name }}' spec: containers: - name: ollama image: ghcr.io/ollama/ollama:latest # Official image imagePullPolicy: IfNotPresent ports: - containerPort: 11434 name: http volumeMounts: - name: ollama-data mountPath: /root/.ollama env: # If you want to pre‑start a model, set this env var to the # model name (e.g., "gpt-4o-mini"). The container will download # it automatically at startup. # - name: OLLAMA_MODEL # value: "gpt-4o-mini" readinessProbe: httpGet: scheme: HTTP path: /api/status port: 11434 initialDelaySeconds: 5 periodSeconds: 10 successThreshold: 1 failureThreshold: 3 resources: requests: cpu: 500m memory: 1Gi limits: cpu: 2000m memory: 4Gi volumes: - name: ollama-data persistentVolumeClaim: claimName: '{{ .Release.Name }}-data'